Fusing semantic aspects for image annotation and retrieval

doi:10.1016/j.jvcir.2010.06.004

	Fusing semantic aspects for image annotation and retrieval
	Li, Zhixin 1,2; Shi, Zhiping 1,3; Liu, Xi 1; Li, Zhiqing 1; Shi, Zhongzhi 1
	2010-11-01
发表期刊	JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
ISSN	1047-3203
卷号	21 期号:8 页码:798-805
摘要	In this paper, we present an approach based on probabilistic latent semantic analysis (PLSA) to achieve the task of automatic image annotation and retrieval. In order to model training data precisely, each image is represented as a bag of visual words. Then a probabilistic framework is designed to capture semantic aspects from visual and textual modalities, respectively. Furthermore, an adaptive asymmetric learning algorithm is proposed to fuse these aspects. For each image document, the aspect distributions of different modalities are fused by multiplying different weights, which are determined by the visual representations of images. Consequently, the probabilistic framework can predict semantic annotation precisely for unseen images because it associates visual and textual modalities properly. We compare our approach with several state-of-the-art approaches on a standard Corel dataset. The experimental results show that our approach performs more effectively and accurately. (c) 2010 Elsevier Inc. All rights reserved.
关键词	Automatic image annotation Latent aspect model PLSA Adaptive asymmetric learning Image retrieval Semantic gap Visual feature Textual word
DOI	10.1016/j.jvcir.2010.06.004
收录类别	SCI
语种	英语
资助项目	National Basic Research Priorities Programme[2007CB311004] ; National Science and Technology Support Plan[2006BAC08B06] ; National Natural Science Foundation of China[60775035] ; National Natural Science Foundation of China[60933004] ; National Natural Science Foundation of China[60903141] ; National Natural Science Foundation of China[60970088] ; National Natural Science Foundation of China[60903079]
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering
WOS记录号	WOS:000283827500004
出版者	ACADEMIC PRESS INC ELSEVIER SCIENCE
引用统计	被引频次：14[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/12217
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Zhixin
作者单位	1.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China 2.Guangxi Normal Univ, Coll Comp Sci & Informat Technol, Guilin 541004, Peoples R China 3.Capital Normal Univ, Informat Engn Coll, Beijing 100048, Peoples R China
推荐引用方式 GB/T 7714	Li, Zhixin,Shi, Zhiping,Liu, Xi,et al. Fusing semantic aspects for image annotation and retrieval[J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION,2010,21(8):798-805.
APA	Li, Zhixin,Shi, Zhiping,Liu, Xi,Li, Zhiqing,&Shi, Zhongzhi.(2010).Fusing semantic aspects for image annotation and retrieval.JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION,21(8),798-805.
MLA	Li, Zhixin,et al."Fusing semantic aspects for image annotation and retrieval".JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 21.8(2010):798-805.